iFSQ: Improving FSQ for Image Generation with 1 Line of Code Paper • 2601.17124 • Published Jan 23 • 33
CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance Paper • 2503.10391 • Published Mar 13, 2025 • 12
Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models Paper • 2601.07287 • Published Jan 12 • 5
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 52